DeepSeek R1

🔥 Top Reasoner
🏢 DeepSeek ⚡ 671B MoE 📖 128K Context 🏷️ reasoning

DeepSeek's breakthrough open-weights reasoning model with long chain-of-thought and stellar math/coding benchmark scores.

🏢 Free Providers
7 (7 在线)
1 条国内高速 BGP 直连线路
⚡ Lowest Latency
240ms
基于 FreeAI 全网边缘探活实测
🛡️ Overall SLA
99.9%
智能故障检测 · 多端点热备
🎁 Official Price
$0 Permanent Free
无隐藏门槛 · 开发者长期公测

📡 All Free Providers Live Radar

Ranked by live health & lowest latency. Copy provider model ID or claim free keys directly.

🟢 动态探活排序
#1

Cloudflare Workers AI

models.global_route 🟢 240ms
Model ID: @cf/deepseek-ai/deepseek-r1-distill-qwen-32b
🎁 10,000 Neurons free compute daily (Global 300+ edge nodes · Daily reset)
#2

SiliconFlow

Direct CN 🟢 274ms
Model ID: deepseek-ai/DeepSeek-R1
🎁 Free ¥16 credit voucher upon verification (180d validity) (Covers ~1,600 tokens · No card required)
#3

NVIDIA NIM

models.global_route 🟢 274ms
Model ID: deepseek-ai/deepseek-r1
🎁 Free 1,000 trial credits (NVIDIA enterprise container · 40 RPM)
#4

Together AI

models.global_route 🟢 280ms
Model ID: deepseek-ai/DeepSeek-R1
🎁 Free $5 trial bonus on signup (Low-latency distributed inference cluster)
#5

Novita AI

models.global_route 🟢 281ms
Model ID: deepseek/deepseek-r1
🎁 新用户注册赠送体验金 ($1 ~ $50) (64k Context · 试用期内有效 (90天))
#6

GitHub Models

models.global_route 🟢 304ms
Model ID: DeepSeek-R1
🎁 150 free calls daily for GitHub accounts (Azure high-availability hosting · Free dev tier)
#7

SambaNova Cloud

models.global_route 🟢 304ms
Model ID: DeepSeek-R1
🎁 200,000 free tokens daily (SN40L hardware acceleration · No card)

💻 Quick Start Code Example

Fully compatible with OpenAI SDK. Replace the API Key and execute directly in Python or cURL.

from openai import OpenAI

# 1. 替换为对应厂商领取的 API Key 与 Base URL (参见下方厂商雷达表)
client = OpenAI(
    api_key="your_api_key_here",
    base_url="https://api.siliconflow.cn/v1"  # 示例: 硅基流动直连端点
)

response = client.chat.completions.create(
    model="@cf/deepseek-ai/deepseek-r1-distill-qwen-32b",
    messages=[
        {"role": "system", "content": "You are a helpful AI assistant."},
        {"role": "user", "content": "Hello! Please introduce yourself briefly."}
    ],
    temperature=0.6,
    stream=True
)

for chunk in response:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
curl https://api.siliconflow.cn/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your_api_key_here" \
  -d '{
    "model": "@cf/deepseek-ai/deepseek-r1-distill-qwen-32b",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ],
    "temperature": 0.7
  }'